INDEX

Explanations

points of dialogue that convey intentions or requests

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 bewust

-0.47

iconque

-0.44

 récemment

-0.44

 Kebijakan

-0.43

 eût

-0.43

 consciente

-0.42

 zależ

-0.42

 Absicht

-0.41

 Lingkungan

-0.41

Général

-0.41

POSITIVE LOGITS

 ModelExpression

0.69

ExtendWith

0.52

 tomorrow

0.51

ReusableCell

0.48

XtraReports

0.48

 oprot

0.47

httphttps

0.45

 للاسماء

0.45

ConstraintMaker

0.44

oredCriteria

0.44

Activations Density 0.259%

points of dialogue that convey intentions or requests

No Comments

No Known Activations